A team at DisneyResearch in Los Angeles used a proprietary Audio-Animatronics humanoid bust that had responsive cameras in its eyes and subjected it to interactive situations. The goal of this experiment was to learn how to create highly realistic gaze engagement for true character believability in films. The categories of these incredible interactions include the default state of “Read”, the transition state of “Glance”, the alert state of “Engage”, and the active state of “Acknowledge”, all culminating in eerily humanlike, anthropomorphic responses.
We present a general architecture that seeks not only to create gaze interactions from a technological standpoint, but also through the lens of character animation where the fidelity and believability of motion is paramount; that is we seek to create an interaction which demonstrates the illusion of life.
